• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Transferring Experience from Simulation to the Real World for Precise Pick-And-Place Tasks in Highly Cluttered Scenes
 
  • Details
  • Full
Options
2020
Conference Paper
Title

Transferring Experience from Simulation to the Real World for Precise Pick-And-Place Tasks in Highly Cluttered Scenes

Abstract
In this paper, we introduce a novel learning-based approach for grasping known rigid objects in highly cluttered scenes and precisely placing them based on depth images. Our Placement Quality Network (PQ-Net) estimates the object pose and the quality for each automatically generated grasp pose for multiple objects simultaneously at 92 fps in a single forward pass of a neural network. All grasping and placement trials are executed in a physics simulation and the gained experience is transferred to the real world using domain randomization. We demonstrate that our policy successfully transfers to the real world. PQ-Net outperforms other model-free approaches in terms of grasping success rate and automatically scales to new objects of arbitrary symmetry without any human intervention.
Author(s)
Kleeberger, Kilian  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Völk, Markus  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Moosmann, Marius  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Thiessenhusen, Erik
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Roth, Florian  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Bormann, Richard  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Huber, Marco  
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Mainwork
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020  
Conference
International Conference on Intelligent Robots and Systems (IROS) 2020  
Link
Link
Language
English
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA  
Keyword(s)
  • bin-picking

  • maschinelles Sehen

  • maschinelles Lernen

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024